“…At the same time, because LSTM can apply historical data to the prediction, historical data can also improve the model prediction accuracy. Tan [109] adopted long and shortterm memory networks to establish the battery SOH decline model. Based on the transfer learning method, the estimation accuracy of the model for different batteries under different conditions and batches was improved.…”
Lithium-ion power batteries have been widely used in transportation due to their advantages of long life, high specific power, and energy. However, the safety problems caused by the inaccurate estimation and prediction of battery health state have attracted wide attention in academic circles. In this paper, the degradation mechanism and main definitions of state of health (SOH) were described by summarizing domestic and foreign literatures. The estimation and prediction methods of lithium-ion power battery SOH were discussed from three aspects: model-based methods, data-driven methods, and fusion technology methods. This review summarizes the advantages and disadvantages of the current mainstream SOH estimation and prediction methods. This paper believes that more innovative feature parameter extraction methods, multi-algorithm coupling, combined with cloud platform and other technologies will be the development trend of SOH estimation and prediction in the future, which provides a reference for health state estimation and prediction of lithium-ion power battery.
“…At the same time, because LSTM can apply historical data to the prediction, historical data can also improve the model prediction accuracy. Tan [109] adopted long and shortterm memory networks to establish the battery SOH decline model. Based on the transfer learning method, the estimation accuracy of the model for different batteries under different conditions and batches was improved.…”
Lithium-ion power batteries have been widely used in transportation due to their advantages of long life, high specific power, and energy. However, the safety problems caused by the inaccurate estimation and prediction of battery health state have attracted wide attention in academic circles. In this paper, the degradation mechanism and main definitions of state of health (SOH) were described by summarizing domestic and foreign literatures. The estimation and prediction methods of lithium-ion power battery SOH were discussed from three aspects: model-based methods, data-driven methods, and fusion technology methods. This review summarizes the advantages and disadvantages of the current mainstream SOH estimation and prediction methods. This paper believes that more innovative feature parameter extraction methods, multi-algorithm coupling, combined with cloud platform and other technologies will be the development trend of SOH estimation and prediction in the future, which provides a reference for health state estimation and prediction of lithium-ion power battery.
“…Obtaining health features, therefore, from the partial charging curves more comply with actual situation. By this manner, the time asked to change from a low voltage to high value is considered and applied as the health feature ( Tan and Zhao, 2020 ), and the specific calculation is formulated as where represents the charging duration from to at the i th cycle and and denote the time to reach and at the i th cycle. Richardson et al.…”
Section: Study Of Feature Extractionmentioning
confidence: 99%
“… denotes the input of current step, and means the output of step . is an internal variable of LSTM cells; means the activation function, and the sigmoid function is usually selected to restrict the output value between 0 and 1; is defined as the hyperbolic function ( Tan and Zhao, 2020 ). Figure 11 Schematic diagram of LSTM …”
Summary
Accurate state of health (SOH) prediction is significant to guarantee operation safety and avoid latent failures of lithium-ion batteries. With the development of communication and artificial intelligence technologies, a body of researches have been performed toward precise and reliable SOH prediction method based on machine learning (ML) techniques. In this paper, the conception of SOH is defined, and the state-of-the-art prediction methods are classified based on their primary implementation procedure. As an essential step in ML-based SOH algorithms, the health feature extraction methods reported in the literature are comprehensively surveyed. Next, an exhausted comparison is conducted to elaborate the development of ML-based SOH prediction techniques. Not only their advantages and disadvantages of the application in SOH prediction are reviewed but also their accuracy and execution process are fully discussed. Finally, pivotal challenges and corresponding research directions are provided for more reliable and high-fidelity SOH prediction.
“…Generally, the prediction methods of SOH can be sorted into three groups: direct calibration methods, filter-based methods and machine learning-based methods [9]. Direct calibration methods determine battery SOH via specific experimental operations, such as full discharge of the battery after a complete charge [10]. This kind of methods are simple and easy to implement.…”
The application of machine learning-based state of health (SOH) prediction is hindered by large demand of training data. To conquer this defect, a flexible and easy transferred SOH prediction scheme for lithium-ion battery packs is developed. Firstly, the charging duration for a predefined voltage range is hired as the health feature to quantify capacity degradation. Then, the long short-term memory (LSTM) network and transfer learning (TL) with fine-tuning strategy are incorporated to constitute the cell mean model (CMM) for SOH prediction with partial training data. Next, to evaluate the SOH inconsistencies among cells, the LSTM model is employed as the cell difference model (CDM), and the minimum estimation value of CDM is identified to determine pack SOH. The experimental results reveal that even when the first 360 cycle data, occupying only 40% in the whole 904 cycle data, are chosen and constituted to the dataset for model training, the obtained estimation algorithm can still predict SOH precisely with the error of less than 3%, thus remarkably reducing the training data amount and mitigating the computation burden during model training. In addition, the preferable validation results on different types of lithium-ion batteries further manifest the extendibility of the proposed strategy. Index Terms-Lithium-ion battery pack, long short-term memory (LSTM), transfer learning (TL), state of health (SOH).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citationsâcitations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
